Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Liyuchen0118/RunBeacon --skill monitor-remote-jobsgit clone --depth 1 https://github.com/Liyuchen0118/RunBeaconWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/liyuchen0118/runbeacon/monitor-remote-jobs)<a href="https://agentmods.dev/skills/liyuchen0118/runbeacon/monitor-remote-jobs"><img src="https://agentmods.dev/badge/skills/liyuchen0118/runbeacon/monitor-remote-jobs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/liyuchen0118/runbeacon/monitor-remote-jobs"><img src="https://agentmods.dev/badge/skills/liyuchen0118/runbeacon/monitor-remote-jobs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00104 | $0.02906 |
| Opus 5 | $0.00052 | $0.01453 |
| Sonnet 5 | $0.00021 | $0.00581 |
| Haiku 4.5 | $0.00010 | $0.00291 |
Grade A, and why
monitor-remote-jobs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monitor Remote Jobs with RunBeacon
Use RunBeacon as the default route for non-interactive work on a remote machine, even when the user only says to run, deploy, inspect, or monitor something "on the server." Route any command whose completion matters through the plugin's tracked job tools. The plugin can only observe processes and SSH channels that it launches.
Availability contract
RunBeacon is available only when its MCP tools are registered in the current Codex task. If job_start is not exposed, fail fast and tell the user to start a new task after reinstalling the plugin. Do not launch lifecycle-server.js through a shell or bypass MCP with raw SSH. The MCP App is the primary dashboard; the interactive runbeacon dashboard CLI may create an on-demand loopback page when the host has no Apps capability, but the model must not start that fallback automatically.
Run and continue
For a request that already contains a complete command and explicitly selects the default SSH server, take the zero-exploration fast path: after reading this skill, make job_start the first task action with the command copied verbatim and useDefaultCredential: true. Do not inspect the current directory, README, tests, plugin source, tool registry, or credential profiles, and do not reconstruct or escape the command in JavaScript.
- Call
job_startwith the complete command,executionMode: "auto", and optional label, timeout, adapter, output policy, RE2 progress regex, and subscriptions. SetrequireDurable: truefor training that must survive SSH loss, Slurm, Apple signing, or any workflow that cannot tolerate direct SSH. The Hook attaches the current prompt trace; do not synthesize or replace it.job_startmounts the single-task MCP App immediately. Progress patterns are limited to 256 characters, put the finite percentage in capture group 1, and cannot use backreferences or lookaround. Reusable operations should also provide a stableidempotencyKey. - Record the returned
jobId. - As the very next tool call, immediately call
job_waitonce with thatjobId. Do not insert commentary, documentation reads, credential listing, status inspection, or additional planning betweenjob_startandjob_wait. Do not build a sleep/status loop and do not repeatedly calljob_snapshot. - After
job_waitreturns a terminal state, inspect its bounded output tail and continue the user's requested next step. - If the server-side wait itself times out while the job is still running, tell the user and call
job_waitat most once more when continued waiting is intended.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 102 lines · 104 tokens per session scan A ba5e20fbe0a3
monitor-remote-jobs is a skill published in the GitHub repository Liyuchen0118/RunBeacon (2 stars, last pushed 2d ago), licensed MIT. It adds 104 tokens to every session and 2,906 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ship
Use when code is ready to ship — creates PRs, merges, deploys, and verifies. Handles the full PR-to-production pipeline. Triggers on /ship.
deploy-preview
Deploy a preview branch to the staging environment for review. Use when a feature branch is ready for visual review, when someone asks to "deploy this for review", or before opening a PR.
release-deploy
Prepare a public open-source project for release and deploy it to a detected target. Use at a release or submission boundary to verify setup, docs, secrets, tests, lint, build, and licenses, then follow the target-specific deployment path. Runs expensive checks sequentially. Never publishes, tags, commits, pushes, or…
setup-convex-worktrees
Set up, repair, or explain isolated Convex development deployments for Git worktrees and coding agents, including per-worktree env bindings, temporary deployment creation, baseline data seeding, frontend port isolation, and AGENTS.md guardrails. Use when separate checkouts are clobbering one shared Convex dev…
ship
Use when work should go live — commit, push, deploy per recipe, cache-busted live verify, smoke, screenshot. Blocks the "shipped" claim on the live check.
sc:deploy-remote
Deploy / sync the current LOCAL workspace to its linked REMOTE host over SSH, and manage that remote (create dirs, run commands, restart services) — all from the local workspace. Use when the user asks to deploy, push to production, sync to the server/remote, ship, release, or "handle the remote". Reads the…